Exercise 1

Open NGPhylogeny.fr.
Click on “Let’s go! with One Click Workflow”
Choose FASTME/OneClick in Select your workflow
Either input the “tree phylogenetic tree” or copy and paste the amino acid sequence from the file downloaded.
Hit submit
Download output tree file

TreeImage

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(ggtree)

## Registered S3 method overwritten by 'treeio':
##   method     from
##   root.phylo ape

## ggtree v2.2.4  For help: https://yulab-smu.github.io/treedata-book/
## 
## If you use ggtree in published research, please cite the most appropriate paper(s):
## 
## [36m-[39m Guangchuang Yu. Using ggtree to visualize data on tree-like structures. Current Protocols in Bioinformatics, 2020, 69:e96. doi:10.1002/cpbi.96
## [36m-[39m Guangchuang Yu, Tommy Tsan-Yuk Lam, Huachen Zhu, Yi Guan. Two methods for mapping and visualizing associated data on phylogeny using ggtree. Molecular Biology and Evolution 2018, 35(12):3041-3043. doi:10.1093/molbev/msy194
## [36m-[39m Guangchuang Yu, David Smith, Huachen Zhu, Yi Guan, Tommy Tsan-Yuk Lam. ggtree: an R package for visualization and annotation of phylogenetic trees with their covariates and other associated data. Methods in Ecology and Evolution 2017, 8(1):28-36. doi:10.1111/2041-210X.12628

## 
## Attaching package: 'ggtree'

## The following object is masked from 'package:tidyr':
## 
##     expand

library(treeio)

## treeio v1.12.0  For help: https://yulab-smu.github.io/treedata-book/
## 
## If you use treeio in published research, please cite:
## 
## LG Wang, TTY Lam, S Xu, Z Dai, L Zhou, T Feng, P Guo, CW Dunn, BR Jones, T Bradley, H Zhu, Y Guan, Y Jiang, G Yu. treeio: an R package for phylogenetic tree input and output with richly annotated and associated data. Molecular Biology and Evolution 2020, 37(2):599-603. doi: 10.1093/molbev/msz240

library(ggimage)

Exercise 2

TOL_output.mafft

tt <- read.tree("data/fastree_result.tre")
tt

## 
## Phylogenetic tree with 21 tips and 19 internal nodes.
## 
## Tip labels:
##   Archaeoglobus_fulgidus, Trypanosoma_cruzi_nuclear, Amphidinium_carterae, Saccharomyces_cerevisiae_nuclear, Homo_sapies_nuclear, Drosophila_yakuba_nuclear, ...
## Node labels:
##   , 0.999, 0.856, 1.000, 0.988, 0.979, ...
## 
## Unrooted; includes branch lengths.

ggtree(tt) + geom_tiplab()

Exercise 3

library(tidyverse)
library(ggtree)
library(treeio)
library(ggimage)

tree <- read.tree("data/tree_newick.nwk")
tree

## 
## Phylogenetic tree with 13 tips and 12 internal nodes.
## 
## Tip labels:
##   A, B, C, D, E, F, ...
## 
## Rooted; includes branch lengths.

ggplot(tree) + geom_tree() + theme_tree()

ggtree(tree)

adding a scale

ggtree(tree) + geom_treescale()

ggtree(tree) + theme_tree2()

ggtree(tree, branch.length="none")

ggtree(tree, branch.length="none", color="blue", size=2, linetype=3)

Exercise 1

ggtree(tree, layout = "slanted")

ggtree(tree, layout = "circular")

ggtree(tree, branch.length="none", color="red", size=2, linetype=1)

#———————————————————————————————–

Other tree genomes

# create the basic plot
p <- ggtree(tree)

Node points, tip points and tiplab

p + geom_nodepoint() + geom_tippoint() + geom_tiplab()

Exercise 2

p + geom_tippoint(shape = "diamond", color = "purple") + geom_tiplab(color = "purple") + geom_nodepoint(color = "yellow", alpha = 0.5, size = 3)

Tree annotation

ggtree(tree) + geom_text(aes(label=node), hjust=-.1)

ggtree(tree) + geom_tiplab()

Labelling Clades

ggtree(tree) + 
  geom_cladelabel(node=17, label="Random", color="red", offset =.8, align = TRUE)+
  geom_cladelabel(node=21, label="Different", 
                  color="blue", offset=.8, align = TRUE) +
 theme_tree2() + 
  xlim(0, 70)

removing x-axis scale

ggtree(tree) + 
  geom_cladelabel(node=17, label="Random", color="red", offset =.8, align = TRUE)+
  geom_cladelabel(node=21, label="Different", 
                  color="blue", offset=.8, align = TRUE) +
 theme_tree2() + 
  xlim(0, 70) + 
  theme_tree()

highlight the entire clade

ggtree(tree) + 
  geom_tiplab() + 
  geom_hilight(node=17, fill="gold") + 
  geom_hilight(node=21, fill="purple")

ggtree(tree) + geom_tiplab()

MRCA(tree, c("C", "E"))

## [1] 17

MRCA(tree, c("G", "H"))

## [1] 21

Connecting Taxa

(use geom_taxalink())

ggtree(tree) + 
  geom_tiplab() + 
  geom_taxalink("E", "H", color="blue3") +
  geom_taxalink("C", "G", color="orange2", curvature=-.9)

Exercise 3

ggtree(tree) + geom_text(aes(label=node), hjust=-.3)

ggtree(tree)

MRCA(tree, c("B", "C"))

## [1] 19

MRCA(tree, c("L", "J"))

## [1] 23

ggtree(tree) + 
  geom_tiplab() +
  geom_hilight(node=19, fill="sky blue") + 
  geom_hilight(node=23, fill="lavender") + 
  geom_taxalink("C", "E", linetype = 2) +
  geom_taxalink("G", "J", linetype = 2) + 
  theme_tree2() + 
  ggtitle("Practice Phylogenetic tree")

  ggtree(tree, layout = "circular") +
  geom_tiplab() +
  geom_hilight(node=19, fill="sky blue") + 
  geom_hilight(node=23, fill="lavender") + 
  theme_tree2() + 
  ggtitle("Practice Phylogenetic circular tree")

Read the data

tree <- read.beast("data/flu_tree_beast.tree")
tree

## 'treedata' S4 object that stored information of
##  'data/flu_tree_beast.tree'.
## 
## ...@ phylo: 
## Phylogenetic tree with 76 tips and 75 internal nodes.
## 
## Tip labels:
##   A/Hokkaido/30-1-a/2013, A/New_York/334/2004, A/New_York/463/2005, A/New_York/452/1999, A/New_York/238/2005, A/New_York/523/1998, ...
## 
## Rooted; includes branch lengths.
## 
## with the following features available:
##  'height',   'height_0.95_HPD',  'height_median',    'height_range', 'length',
##  'length_0.95_HPD',  'length_median',    'length_range', 'posterior',    'rate',
##  'rate_0.95_HPD',    'rate_median',  'rate_range'.

Scale Bar

ggtree(tree, mrsd="2013-01-01") + 
  theme_tree2()

Finally, add tip labels and adjust axis

ggtree(tree, mrsd="2013-01-01") + 
  theme_tree2() + 
  geom_tiplab(align=TRUE, linesize=.5) + 
  xlim(1990, 2020)

msaplot(p=ggtree(tree), fasta="data/flu_aasequence.fasta", window=c(150, 175))

set.seed(42)
trees <- lapply(rep(c(10, 25, 50, 100), 3), rtree)
class(trees) <- "multiPhylo"
ggtree(trees) + facet_wrap(~.id, scale="free", ncol=4) + ggtitle("Phylogenetic trees")

tree <- rtree(30)
p <- ggtree(tree)
d1 <- data.frame(id=tree$tip.label, val=rnorm(30, sd=3))
p2 <- facet_plot(p, panel="dot", data=d1, geom=geom_point, aes(x=val), color='red3')
d2 <- data.frame(id=tree$tip.label, value = abs(rnorm(30, mean=100, sd=50)))
p3 <- facet_plot(p2, panel='bar', data=d2, geom=geom_segment, 
           aes(x=0, xend=value, y=y, yend=y), size=3, color='blue4') 
p3 + theme_tree2()

Tree File

tree <- read.tree("data/fastree_result.tre")
tree

## 
## Phylogenetic tree with 21 tips and 19 internal nodes.
## 
## Tip labels:
##   Archaeoglobus_fulgidus, Trypanosoma_cruzi_nuclear, Amphidinium_carterae, Saccharomyces_cerevisiae_nuclear, Homo_sapies_nuclear, Drosophila_yakuba_nuclear, ...
## Node labels:
##   , 0.999, 0.856, 1.000, 0.988, 0.979, ...
## 
## Unrooted; includes branch lengths.

ggtree(tree) + 
  theme_tree2() +
    geom_tiplab() + 
  geom_nodelab() + 
  xlim(0,2)

ggtree(tree, layout = "circular") + 
  theme_tree2() +
    geom_tiplab() + 
  geom_nodelab() + 
  xlim(0,36)

Exercise 4

library(ggtree)

Output_tree.nhx

nhxfile <- read.tree("data/Output_Tree.nhx")
nhxfile

## 
## Phylogenetic tree with 21 tips and 19 internal nodes.
## 
## Tip labels:
##   Oryza_mitochondrion, Rhizobium_leguminosarum, Escherichia_coli_, Burkholderia_cenocepacia_, Chlorobium_chlorochromatii, Oryza_chloroplast, ...
## 
## Unrooted; includes branch lengths.

ggtree(nhxfile) + geom_text(aes(label=node), hjust=-.3)

ggtree(nhxfile) +
    geom_nodelab()+
  geom_tiplab(hjust=-.1, size = 3) +
    geom_hilight(node=23, fill="gold", extend = 0.5) + 
    geom_hilight(node=37, fill="purple", extend = 0.8) + 
    geom_hilight(node=27, fill="blue", extend = 0.5)

xlim(0,36)

## <ScaleContinuousPosition>
##  Range:  
##  Limits:    0 --   36

ggtree(nhxfile, layout = "circular") +
    geom_nodelab()+
  geom_tiplab(hjust=-.1, size = 3) +
    geom_hilight(node=23, fill="gold", extend = 0.5) + 
    geom_hilight(node=37, fill="purple", extend = 0.5) + 
    geom_hilight(node=27, fill="blue", extend = 0.5)

xlim(0,36)

## <ScaleContinuousPosition>
##  Range:  
##  Limits:    0 --   36

Lab8: Sequence Alignment, Phylogenetic Analysis and Tree Visualization

Manya Vivek

10/19/2020

Exercise 1

Exercise 2

Exercise 3

adding a scale

Exercise 1

Other tree genomes

Node points, tip points and tiplab

Exercise 2

Tree annotation

Labelling Clades

removing x-axis scale

highlight the entire clade

Connecting Taxa

(use geom_taxalink())

Exercise 3

Read the data

Scale Bar

Finally, add tip labels and adjust axis

Exercise 4